Tap a claim on the ring to put it at the centre.
← Harness engineering is raising the floor: optimising the environment a…
17 connected korrents · 17 moments from 18 Sept 2025 to 15 Oct 2026.
Everything filed under coding agents
coding agents
Everything filed under Anthropic
Anthropic
Everything filed under AI agents
AI agents
Everything filed under software quality
software quality
Everything filed under LLMs
LLMs
Everything filed under developer tools
developer tools
Everything filed under vibe coding
vibe coding Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Read this korrent: Harness engineering is raising the floor: optimising the environment a coding agent runs in so that the results of every single turn are as good as possible. Harness engineering is raising the floor: optimising the environment a coding agent runs in so that the results of every single turn are as good as possible. Last stated 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: The winning move in coding agents was inverted: take share with a merely good-enough harness first, then go back and make the harness smart. — tap to centre the map on it The winning move in coding agents was inverted: take share with a merely good-enough harness first, then go back and make the harness smart. Last stated 5 months ago
27 May 2026
DR
Dax Raad — holds since 2026-05-27 — tap for who they are
Same subject: When an AI lab builds both a model and a coding harness, the model is optimized for that lab's own harness first. — tap to centre the map on it When an AI lab builds both a model and a coding harness, the model is optimized for that lab's own harness first. Last stated 4 months ago
27 Jun 2026
SR
Sebastian Raschka — holds since 2026-06-27 — tap for who they are
Same subject: What made Claude Code better than every CLI coding agent before it was reinforcement learning on the model and the harness together, so the model got good at that harness’s specific tools. — tap to centre the map on it What made Claude Code better than every CLI coding agent before it was reinforcement learning on the model and the harness together, so the model got good at that harness’s specific tools. Last stated 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: Having the very best AI model and harness does not result in better or faster execution and can slow teams down — tap to centre the map on it Having the very best AI model and harness does not result in better or faster execution and can slow teams down Last stated a month ago
19 Sept 2026
GO
Gergely Orosz — holds since 2026-09-19 — tap for who they are
Same subject: A good tool raises the floor of what people can build without lowering the ceiling, and almost every tool quietly lowers the ceiling. — tap to centre the map on it A good tool raises the floor of what people can build without lowering the ceiling, and almost every tool quietly lowers the ceiling. Last stated a year ago
18 Sept 2025
TL
Tobias Lütke — holds since 2025-09-18 — tap for who they are
Same subject: Increasing time spent with coding agents strengthens the conviction that they make software engineering even harder. — tap to centre the map on it Increasing time spent with coding agents strengthens the conviction that they make software engineering even harder. Last stated 4 weeks ago
24 Sept 2026
SW
Simon Willison — holds since 2026-09-24 — tap for who they are
Same subject: Two new AI models, paired with their coding agent harnesses, improved from often making mistakes to being reliable enough for day-to-day use. — tap to centre the map on it Two new AI models, paired with their coding agent harnesses, improved from often making mistakes to being reliable enough for day-to-day use. Last stated 4 weeks ago
27 Sept 2026
SW
Simon Willison — holds since 2026-09-27 — tap for who they are
Same subject: Many tech companies that build their own coding agent harnesses will likely build internal vibe-coding tools for non-engineers. — tap to centre the map on it Many tech companies that build their own coding agent harnesses will likely build internal vibe-coding tools for non-engineers. Last stated a week ago
15 Oct 2026
GO
Gergely Orosz — holds since 2026-10-15 — tap for who they are
Same subject: A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year. — tap to centre the map on it A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year. Last stated 2 months ago
3 Sept 2026
DR
Dax Raad — holds since 2026-09-03 — tap for who they are
Same subject: A skill is a set of repeatable, specific instructions that augments what Claude Code can do. — tap to centre the map on it A skill is a set of repeatable, specific instructions that augments what Claude Code can do. Last stated 7 months ago
19 Mar 2026
KP
Kris Puckett — holds since 2026-03-19 — tap for who they are
Same subject: A story's quality depends on whether it engages and satisfies the reader, not on the tool used to write it. — tap to centre the map on it A story's quality depends on whether it engages and satisfies the reader, not on the tool used to write it. Last stated 2 months ago
30 Aug 2026
EP
Eliot Peper — holds since 2026-08-30 — tap for who they are
Same subject: 95 percent of the software made in an age of abundance will be shitty, and shitty software is easy to deal with because it goes away. — tap to centre the map on it 95 percent of the software made in an age of abundance will be shitty, and shitty software is easy to deal with because it goes away. Last stated 4 weeks ago
23 Sept 2026
GT
Geoff Teehan — holds since 2026-09-23 — tap for who they are
Same subject: A feature added to a codebase is extremely difficult to remove once other code is built on top of it. — tap to centre the map on it A feature added to a codebase is extremely difficult to remove once other code is built on top of it. Last stated 2 months ago
1 Sept 2026
VB
Vicki Boykis — holds since 2026-09-01 — tap for who they are
Same subject: A feature shipped in a product's official release is fair to judge, regardless of whether the company labels it a beta. — tap to centre the map on it A feature shipped in a product's official release is fair to judge, regardless of whether the company labels it a beta. Last stated a month ago
14 Sept 2026
JS
Jason Snell — holds since 2026-09-14 — tap for who they are
Same subject: A collection of AI agents does not automatically form a functioning organization any more than a group of smart people does. — tap to centre the map on it A collection of AI agents does not automatically form a functioning organization any more than a group of smart people does. Last stated 5 months ago
21 May 2026
RK
Rohit Krishnan — holds since 2026-05-21 — tap for who they are
Same subject: A company cannot be led by machines, because nobody would have recourse against them. — tap to centre the map on it A company cannot be led by machines, because nobody would have recourse against them. Last stated a month ago
15 Sept 2026
TL
Tobias Lütke — holds since 2026-09-15 — tap for who they are
Same subject: A computer-using agent needs a machine of its own, or you will spend the day fighting it for the mouse cursor. — tap to centre the map on it A computer-using agent needs a machine of its own, or you will spend the day fighting it for the mouse cursor. Last stated 2 months ago
10 Aug 2026
PS
Peter Steinberger — holds since 2026-08-10 — tap for who they are
At the centre
Harness engineering is raising the floor: optimising the environment a coding agent runs in so that the results of every single turn are as good as possible.
Holds Read this korrent →
The winning move in coding agents was inverted: take share with a merely good-enough harness first, then go back and make the harness smart.
Holds
When an AI lab builds both a model and a coding harness, the model is optimized for that lab's own harness first.
Holds
What made Claude Code better than every CLI coding agent before it was reinforcement learning on the model and the harness together, so the model got good at that harness’s specific tools.
Holds
Having the very best AI model and harness does not result in better or faster execution and can slow teams down
Holds
A good tool raises the floor of what people can build without lowering the ceiling, and almost every tool quietly lowers the ceiling.
Holds
Increasing time spent with coding agents strengthens the conviction that they make software engineering even harder.
Holds
Two new AI models, paired with their coding agent harnesses, improved from often making mistakes to being reliable enough for day-to-day use.
Holds
Many tech companies that build their own coding agent harnesses will likely build internal vibe-coding tools for non-engineers.
Holds
A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year.
Holds
A skill is a set of repeatable, specific instructions that augments what Claude Code can do.
Holds
A story's quality depends on whether it engages and satisfies the reader, not on the tool used to write it.
Holds
95 percent of the software made in an age of abundance will be shitty, and shitty software is easy to deal with because it goes away.
Holds
A feature added to a codebase is extremely difficult to remove once other code is built on top of it.
Holds
A feature shipped in a product's official release is fair to judge, regardless of whether the company labels it a beta.
Holds
A collection of AI agents does not automatically form a functioning organization any more than a group of smart people does.
Holds
A company cannot be led by machines, because nobody would have recourse against them.
Holds
A computer-using agent needs a machine of its own, or you will spend the day fighting it for the mouse cursor.
Holds